This review study looks at current advancements in sleepiness detection technologies to address the urgent problem of driving while sleepy leading to accidents. In order to prevent future accidents, it analyzes several approaches and technology and emphasizes how crucial it is to correctly recognize drowsy conditions in drivers. Important results highlight the effectiveness of methods for real-time drowsiness detection such as convolutional neural networks (CNNs), eye aspect ratio (EAR) analysis, and deep learning integration. Additionally, improvements in computer vision algorithms make it possible to precisely analyze facial landmarks and eye blinking patterns, which improves the accuracy of detection systems. In order to protect driver comfort and system reliability, the evaluation emphasizes the importance of non-intrusive fatigue detection techniques while also emphasizing the necessity to reduce false warnings. Remarkably, certain models detect drowsy-eye with an accuracy of above 95%. All things considered, the review emphasizes how important cutting-edge technology is in reducing the risks related to drunk driving, especially deep learning and computer vision algorithms. It promotes the deployment of reliable sleepiness detection technologies in order to increase road safety and reduce accidents brought on by fatigued drivers. Key Words: Drowsiness detection, Eye blink duration, Facial landmark detection, Deep learning algorithms, Computer vision, Eye aspect ratio, Road safety.
Read full abstract